llama.cpp b8665 with CUDA

llama.cpp b8665 with CUDA Support

Pre-built binaries of llama.cpp with CUDA support for multiple CUDA versions.

Source: https://github.com/ggml-org/llama.cpp/releases/tag/b8665
Commit: b8635075ffe27b135c49afb9a8b5c434bd42c502

CUDA Versions

• CUDA 12.8 - Architectures: 7.5, 8.0, 8.6, 8.9, 9.0, 10.0, 12.0

Architecture Reference

• 7.5: Tesla T4, RTX 20xx series, Quadro RTX
• 8.0: A100
• 8.6: RTX 3000 series
• 8.9: RTX 4000 series, L4, L40
• 9.0: H100, H200
• 10.0: B200
• 12.0: RTX Pro series, RTX 50xx

Usage

Download the appropriate tarball for your CUDA version and extract:

tar -xzf llama.cpp-b8665-cuda-12.8.tar.gz
./llama-cli --help